# generated by /homes/nber/adrepec/bin/nbrred running on mysql0
Template-Type: ReDIF-Paper 1.0
Title: Migration Flows and Their Determinants: A Comparative Study of Internal Migration in Italy and the U.S.A.
Author-Name: Swarnjit S. Arora
Number: 0026
Creation-Date: 1974-01
Order-URL: http://www.nber.org/papers/w0026
File-URL: http://www.nber.org/papers/w0026.pdf
File-Format: application/pdf
Abstract: This paper has two goals: first to describe a theoretical model which derives relationships among migration decisions explicitly from utility maximization under uncertainty; and second, to examine why nations vary in their internal migration. To explain variation in internal migration, we hypothesize that the degree of monetization and industrialization of an economy is inversely related to the family cohesiveness; hence, a given percentage increase in relative income will have higher migratory effect in a relatively more monetized economy. The availability of higher initial information and better transportation systems in these economies strongly complement this effect. These hypothesis are confirmed by the estimates based on the U.S. and Italian data.
Handle: RePEc:nbr:nberwo:0026
Template-Type: ReDIF-Paper 1.0
Title: Production Within the Household
Author-Name: Arleen Leibowitz
Number: 0027
Creation-Date: 1974-01
Order-URL: http://www.nber.org/papers/w0027
File-URL: http://www.nber.org/papers/w0027.pdf
File-Format: application/pdf
Abstract: The amount of time married women spend in workforce has increased dramatically in the last thirty years. This increase in labor force participation has been accompanied by changes in allocation of time to various activities in the household as well. Since the proportion of women in the labor force has been rising, the average amount of time input to household tasks by all women has been declining over the last 50 years. It is valuable to analyze this in the household production context: women choose not simply between work and leisure but between work in the home, work in the market and leisure. This paper will use time budget data to try to determine how women's education levels affect time allocation to various activities.
Handle: RePEc:nbr:nberwo:0027
Template-Type: ReDIF-Paper 1.0
Title: The Wealth Effect in Occupational Choice
Author-Name: Yoram Weiss
Number: 0028
Creation-Date: 1974-01
Order-URL: http://www.nber.org/papers/w0028
File-URL: http://www.nber.org/papers/w0028.pdf
File-Format: application/pdf
Publication-Status: published as International Economic Review, Vol. 17, no. 2 (1976): 292-307.
Abstract: The purpose of this paper is to indicate regularities in the area of occupational choice using income-leisure analysis. A simple one-period model is used to examine the effect of changes in nonhuman and human wealth on the choice of an occupation. It is argued that under certainty: An increase in nonwage income will increase the propensity to choose pleasant low-paying work activities. An increase in human capital will also induce a choice of pleasant work activities if the income effect is dominant. Under conditions of uncertainty an increase in nonwage income will tend to encourage the choice of risky high-paying work activities if their monetary returns are uncertain. If the nonmonetary returns of an occupation are uncertain the propensity to choose it will tend to decrease with wealth. Finally, an increase in human capital is likely to discourage the choice of occupations with risky monetary returns.
Handle: RePEc:nbr:nberwo:0028
Template-Type: ReDIF-Paper 1.0
Title: Male-Female Differences in Wages and Employment: A Specific Human Capital Model
Author-Name: Elisabeth M. Landes
Number: 0029
Creation-Date: 1974-01
Order-URL: http://www.nber.org/papers/w0029
File-URL: http://www.nber.org/papers/w0029.pdf
File-Format: application/pdf
Publication-Status: published as Landes, Elisabeth M. "Sex-Differences In Wages And Employment: A Test Of The Specific Capital Hypothesis," Economic Inquiry, 1977, v15(4), 523-538.
Abstract: This paper analyzes the effects of differential turnover patterns and the existence of firm specific training, jointly financed by employer and employee, on male-female wage and employment differentials. Chapter 1 introduces the topic of sex differences in occupational distribution and compensation and presents some of the more common economic theories which are relevant to the subject. Chapter 2 presents a model of a firm that invests in the training of its workers, where employee turnover represents depreciation on human capital. Differences in the turnover rates of men and women is shown to be an important determinant of the incentive to the employer to hire and train women as well as men. The empirical implications of the model for the relative wage and occupational distribution of women are contrasted with those derived from a model of general human capital investment. Chapter 3 outlines the problems involved in empirical formulation of the model, the choice of the unit of observation for empirical, testing, and data limitations, and presents the results of empirical testing of the model on aggregate occupational data for males and females from the 1967 Survey of Economic Opportunity. In Chapter 4, the model is applied to occupational data from the 1967 Survey of Economic Opportunity for black and white men as an additional test of its applicability and empirical power. Chapter 5 summarizes the empirical findings and conclusions of the paper.
Handle: RePEc:nbr:nberwo:0029
Template-Type: ReDIF-Paper 1.0
Title: The Timing and Spacing of Births and Women's Labor Force Participation: An Economic Analysis
Author-Name: Sue Goetz Ross
Number: 0030
Creation-Date: 1974-01
Order-URL: http://www.nber.org/papers/w0030
File-URL: http://www.nber.org/papers/w0030.pdf
File-Format: application/pdf
Abstract: This dissertation analyzes the timing and spacing of child-births within an economic framework. I have attempted to explain when women in the United States begin child bearing - i.e., the "timing" (of the first birth) - and the length of the interval they spend in child bearing - i.e., the "spacing" of births. Chapter I introduces the topic and reviews some of the relevant literature. In Chapter II, an economic model is developed which predicts that women with a rising price of time over the lifetime will start having their children sooner after finishing school. Those with a high price of time throughout their lifetimes will have their children closer together. The model also predicts that families whose income receipts rise sharply, at least in the early years after the husband enters the labor force, will postpone their first birth and that families with a high lifetime income will have their children farther apart. The data and variables used to test the model's hypotheses are described in Chapter III. Chapters IV and V describe, respectively, the empirical tests of the timing and the spacing hypotheses. The results of an investigation of some relationships between the timing of the various demographic events and labor force participation are reported in Chapter VI. Chapter VII summarizes the theoretical analysis and the empirical results, which generally support the timing and spacing hypotheses.
Handle: RePEc:nbr:nberwo:0030
Template-Type: ReDIF-Paper 1.0
Title: Price Expectations and Household's Demand for Financial Assets
Author-Name: Lester D. Taylor
Number: 0031
Creation-Date: 1974-01
Order-URL: http://www.nber.org/papers/w0031
File-URL: http://www.nber.org/papers/w0031.pdf
File-Format: application/pdf
Abstract: The effects of price expectations on consumption and saving has received relatively little attention, especially at the micro level. This paper's effort is addressed to this void. More specifically, the paper's primary purpose is to investigate whether it is possible to discern empirically a relationship between individually held price expectations and decisions of households to hold particular types of assets. To this end, I have analyzed aggregate time - series data from the National Income Accounts and the Flow-of-Funds and two bodies of micro household data, each involving several thousand households and each containing fairly detailed information on price expectations.
Handle: RePEc:nbr:nberwo:0031
Template-Type: ReDIF-Paper 1.0
Title: Operational Time and Seasonality in Distributed Lag Estimation
Author-Name: Peter K. Clark
Author-Person: pcl65
Number: 0032
Creation-Date: 1974-02
Order-URL: http://www.nber.org/papers/w0032
File-URL: http://www.nber.org/papers/w0032.pdf
File-Format: application/pdf
Abstract: The following paper discusses the analysis of some types of economic time series using an altered time scale, or operational time. It is argued that for some series, observations that are ordinarily thought of as equidistant in time are actually irregularly spaced in a more natural time scale. Section A discusses point or impulse sampling of related series and the estimation of distributed lag relationships between them. Section B discusses time-aggregated sampling. In Section C, operational-time methods are used to calculate the distributed lag relationship between starts and completions for single-family dwellings in the United States. The results are statistically compared with those of ordinary distributed lag methods.
Handle: RePEc:nbr:nberwo:0032
Template-Type: ReDIF-Paper 1.0
Title: Inflation and Market Structure 1967-1973
Author-Name: Phillip Cagan
Number: 0033
Creation-Date: 1974-02
Order-URL: http://www.nber.org/papers/w0033
File-URL: http://www.nber.org/papers/w0033.pdf
File-Format: application/pdf
Publication-Status: published as Explorations in Economic Research, Volume 2, number 2. NBER, 1975.
Abstract: A variety of theories have been offered to explain why prices generally respond so little to declines in demand, and do so now less than formerly. Most of these center around a dependence of prices on costs, or the anticipated trend of costs, and a greater disregard for short-run changes in demand. The more appealing hypothesis is the simple one that price setters tend to adjust slowly to changes in market conditions; they transmit but do not originate inflation. To find that prices in the less competitive markets respond more slowly to changes in market conditions - first lagging, then catching up - would support the theory that firms try to avoid frequent changes in prices but vary in their ability to do so. Are lags in price adjustment related to market structure? Previous empirical studies of the relationship are inconclusive on this point. Earlier literature, largely theoretical, has suggested that concentrated industries tend to raise prices more rapidly, thereby exerting a permanent upward push on the price level. Empirical studies have usually reported the opposite or no consistent relation, however. On the lag-and-catching-up theory, the concentrated industries should exhibit greater increases in the period of waning inflation after 1969. This study examines the data for such a pattern and finds striking evidence of it.
Handle: RePEc:nbr:nberwo:0033
Template-Type: ReDIF-Paper 1.0
Title: Estimation of a Stochastic Model of Reproduction: An Econometric Approach
Author-Name: James J. Heckman
Author-Name: Robert J. Willis
Author-Person: pwi192
Number: 0034
Creation-Date: 1974-02
Order-URL: http://www.nber.org/papers/w0034
File-URL: http://www.nber.org/papers/w0034.pdf
File-Format: application/pdf
Publication-Status: published as Estimation of a Stochastic Model of Reproduction: An Econometric Approach, James J. Heckman, Robert J. Willis. in Household Production and Consumption, Terleckyj. 1976
Abstract: In the past few years, there has been substantial progress in the application of the economic theory of household decision making to human fertility behavior. Theoretical emphasis has been given to the effects of the costs of parental tine and money resources devoted to rearing children on the demand for the total number of children in a static framework under conditions of certainty. Empirical work has focused on explaining variation in the number of children ever born to women, who have completed their childbearing, as a function of measures of the household's total resources and the opportunity cost of time, especially the value of the wife's time. One important objection to static theories of fertility is their failure to deal with the implications of the simple fact that reproduction is a stochastic biological process in which the number and timing of births and the traits of children (e.g. sex, intelligence, health, etc.) are uncertain and not subject to direct control. In this paper, we report some initial results of a study in progress whose goal is to develop an integrated theoretical and econometric model of fertility behavior within a sequential stochastic framework. The principal contribution of the paper is to the development of an appropriate econometric methodology for dealing with some new econometric problems that arise in such models.
Handle: RePEc:nbr:nberwo:0034
Template-Type: ReDIF-Paper 1.0
Title: Changes in the Recession Behavior of Wholesale Prices: The 1920s and Post World War II
Author-Name: Phillip Cagan
Number: 0035
Creation-Date: 1974-03
Order-URL: http://www.nber.org/papers/w0035
File-URL: http://www.nber.org/papers/w0035.pdf
File-Format: application/pdf
Publication-Status: published as Explorations in Economic Research, Volume 2, number 1. National Bureau of Economic Research, Inc, 1975.
Abstract: The present study examines the recession behavior of wholesale prices since World War II and compares it with the 1920s as the most recent period of earlier recessions with comparable severity. The focus is on changes in recession behavior, possible bias in the data, and differences in behavior between various groups of wholesale prices. (Differences between wholesale and consumer prices, though of importance, are not examined here.) The purpose is to extend the evidence on the degree and uniformity of the change in price behavior and to test various interpretations of those changes.
Handle: RePEc:nbr:nberwo:0035
Template-Type: ReDIF-Paper 1.0
Title: Economic Theories of Fertility: What do They Explain?
Author-Name: Warren C. Sanderson
Number: 0036
Creation-Date: 1974-03
Order-URL: http://www.nber.org/papers/w0036
File-URL: http://www.nber.org/papers/w0036.pdf
File-Format: application/pdf
Abstract: This working paper is a draft of a chapter in a larger manuscript which is concerned with the time series variations in fertility in the United States since 1920. This chapter asks how economic models of fertility aid our understanding of our demographic history. Thus little attention is given here to the suitability of economic models for the explanation of cross-sectional fertility differentials.
Handle: RePEc:nbr:nberwo:0036
Template-Type: ReDIF-Paper 1.0
Title: Interpreting Spectral Analyses in Terms of Time-Domain Models
Author-Name: Robert F. Engle
Number: 0037
Creation-Date: 1974-04
Order-URL: http://www.nber.org/papers/w0037
File-URL: http://www.nber.org/papers/w0037.pdf
File-Format: application/pdf
Publication-Status: published as Engle, R., from Annals of Economic and Social Measurements, Vol. 5, 1976.
Publication-Status: published as Interpreting Spectral Analyses in Terms of Time-Domain Models, Robert F. Engle. in Annals of Economic and Social Measurement, Volume 5, number 1, Berg. 1976
Abstract: This paper derives relationships between frequency-domain and standard time-domain distributed-lag and autoregessive moving-average models. These relations are well known in the literature but are presented here in a pedogogic form in order to facilitate interpretation of spectral and cross-spectral analyses. In addition, the paper employs the conventions and discusses the estimation procedures used in TROLL. Some aspects of these estimation procedures are new and have not been discussed in the literature.
Handle: RePEc:nbr:nberwo:0037
Template-Type: ReDIF-Paper 1.0
Title: A General Algorithm for Simultaneous Estimation of Constant and Randomly-Varying Parameters in Lineal Relations
Author-Name: Alexander H. Sarris
Number: 0038
Creation-Date: 1974-04
Order-URL: http://www.nber.org/papers/w0038
File-URL: http://www.nber.org/papers/w0038.pdf
File-Format: application/pdf
Abstract: A recursive algorithm for estimating linear models with both constant and time-varying parameters is derived by maximization of a likelihood function. Recursive formulas are also derived for derivatives of the likelihood function; the derivatives are needed for numerical evaluation of some parameters. Smoothing formulas are also derived. The estimation algorithm is compared with others for similar classes of models.
Handle: RePEc:nbr:nberwo:0038
Template-Type: ReDIF-Paper 1.0
Title: Unemployment Effects of Minimum Wages
Author-Name: Jacob Mincer
Number: 0039
Creation-Date: 1974-05
Order-URL: http://www.nber.org/papers/w0039
File-URL: http://www.nber.org/papers/w0039.pdf
File-Format: application/pdf
Publication-Status: published as Mincer, Jacob. "Unemployment Effects of Minimum Wages." Journal of Political Economy, Part II, (August 1976).
Abstract: Empirical investigation of employment effects of minimum wage legislation is a subject of continuing interest, judging by a growing number of studies. The older studies were concerned mainly with changes in employment in low-wage industries. In the more recent work, attention has shifted to effects on unemployment in low-wage demographic groups, such as teenagers. Despite the statistical difference there is no apparent recognition of a conceptual as well as substantive distinction between minimum wage effects on employment and those on unemployment. The purpose of this paper is to explore the analytical distinction between employment and unemployment effects in the hope of providing some understanding of the observations. Though related empirical work is far from being definitive the findings appear to be informative.
Handle: RePEc:nbr:nberwo:0039
Template-Type: ReDIF-Paper 1.0
Title: Legality and Reality: Some Evidence on Criminal Procedure
Author-Name: William M. Landes
Author-Person: pla327
Number: 0040
Creation-Date: 1974-05
Order-URL: http://www.nber.org/papers/w0040
File-URL: http://www.nber.org/papers/w0040.pdf
File-Format: application/pdf
Publication-Status: published as Landes, William M. "Legality and Reality: Some Evidence on Criminal Procedure." Journal of Legal Studies, (June 1974).
Abstract: There is widespread concern that the criminal justice system, particularly in large urban areas, is breaking down under the strain of an increasing demand for its services and inadequate resources. At the center of the system, located between the police and the prisons, are the criminal courts. Statistics on rising crime rates, recidivism, arbitrary sentencing practices, court delay, and prison riots are taken as further evidence that the courts are failing. What has been notably scarcer is systematic empirical research on the criminal court system - research that can contribute to our understanding of the actual workings of the system and enable us to develop policies for improvement. The purpose of this study is to begin to remedy this deficiency by applying the quantitative techniques of economics to an analysis of some important issues in criminal court procedure.
Handle: RePEc:nbr:nberwo:0040
Template-Type: ReDIF-Paper 1.0
Title: Theories of Economic Regulation
Author-Name: Richard A. Posner
Author-Person: ppo25
Number: 0041
Creation-Date: 1974-05
Order-URL: http://www.nber.org/papers/w0041
File-URL: http://www.nber.org/papers/w0041.pdf
File-Format: application/pdf
Publication-Status: published as Posner, R. A. "Theories Of Economic Regulation," Bell Journal of Economics, 1974, v5(2), 335-358.
Abstract: A major challenge to social theory is to explain the pattern of government intervention in the market - what we may call "economic regulation." Properly defined, the term refers to taxes and subsidies of all sorts as well as to explicit legislative and administrative controls over rates, entry, and other facets of economic activity. Two main theories of economic regulation have been proposed. One is the "public interest" theory, bequeathed by a previous generation of economists to the present generation of lawyers. This theory holds that regulation is supplied in response to the demand of the public for the correction of inefficient or inequitable market practices. It has a number of deficiencies that we shall discuss. The second theory is the "capture" theory - a poor term but one that will do for now. Espoused by an odd mixture of welfare state liberals, Marxists, and free-market economists, this theory holds that regulation is supplied in response to the demands of interest groups struggling among themselves to maximize the incomes of their members. There are crucial differences among the capture theorists. I will argue that the economists' version of the "capture" theory is the most promising but shall also point out the significant weaknesses in both the theory and the empirical research that is alleged to support it.
Handle: RePEc:nbr:nberwo:0041
Template-Type: ReDIF-Paper 1.0
Title: A Theory of Social Interactions
Author-Name: Gary S. Becker
Number: 0042
Creation-Date: 1974-06
Order-URL: http://www.nber.org/papers/w0042
File-URL: http://www.nber.org/papers/w0042.pdf
File-Format: application/pdf
Publication-Status: published as Becker, Gary S. "A Theory of Social Interactions." Journal of Political Economy, Vol. 82, No. 6, (December 1974), pp. 1063-1093.
Abstract: This essay incorporates a general treatment of social interactions into the modern theory of consumer demand. Section 1 introduces the topic and explores some of the existing perspectives on social interactions and their importance in the basic structure of wants. In Section 2, various characteristics of different persons are assumed to affect the utility functions of some persons, and the behavioral implications are systematically explored. Section 3 develops further implications and applications in the context of analyzing intra-family relations, charitable behavior, merit goods and multi-persons interactions, and envy and hatred. The variety and significance of these applications is persuasive testimony not only to the importance of social interactions, but also to the feasibility of incorporating them into a rigorous analysis.
Handle: RePEc:nbr:nberwo:0042
Template-Type: ReDIF-Paper 1.0
Title: Graphics for Data Analysis
Author-Name: Roy E. Welsch
Number: 0043
Creation-Date: 1974-06
Order-URL: http://www.nber.org/papers/w0043
File-URL: http://www.nber.org/papers/w0043.pdf
File-Format: application/pdf
Publication-Status: published as Welsch, Roy E. "Graphics for Data Analysis." Computers and Graphics 2, 1 (1976): 31-37.
Abstract: In recent years, graphics have become an essential part of modern data analysis. This paper describes a system called CLOUDS which is designed to make available on inexpensive storage tube terminals a wide range of graphic tools related to data analysis, economics, and management science. The system can be accessed nationwide by nonprofit organizations via the National Bureau of Economic Research computer network.
Handle: RePEc:nbr:nberwo:0043
Template-Type: ReDIF-Paper 1.0
Title: The Statistical Analysis of Local Structure in Social Networks
Author-Name: Paul W. Holland
Author-Name: Samuel Leinhardt
Number: 0044
Creation-Date: 1974-06
Order-URL: http://www.nber.org/papers/w0044
File-URL: http://www.nber.org/papers/w0044.pdf
File-Format: application/pdf
Abstract: We introduce the concept of a triad census of a digraph arid show how it can be used to enumerate various types of subgraph configurations. We give the basic probabilities needed for computing means and variances for a triad census under the U-MAN distribution for digraphs. These concepts are combined to provide a way of testing propositions about social structure using sociometric data. An application to 408 sociograms is given.
Handle: RePEc:nbr:nberwo:0044
Template-Type: ReDIF-Paper 1.0
Title: The Incubator Hypothesis: Evidence from Five Cities
Author-Name: Robert A. Leone
Author-Name: Raymond Struyk
Number: 0045
Creation-Date: 1974-06
Order-URL: http://www.nber.org/papers/w0045
File-URL: http://www.nber.org/papers/w0045.pdf
File-Format: application/pdf
Abstract: The purpose of this paper is to review the past evidence and to offer some new data to assess whether the incubator hypothesis can be empirically supported. In particular the two general aspects of the hypothesis will be tested. First, we will examine the proposition that highly centralized locations are attracting a disproportionate number of new firms and/or the employment associated with new firms. Second, we will test the hypothesis that new firms which are formed in high density areas move outward from such sites in their early years of existence in order to expand their productive activities. We refer to these as the "simple and "dynamic" hypotheses in the rest of the paper. Our analysis is based on the experience of all manufacturers in several U.S. cities. We recognize that it is quite possible that the hypothesis could hold for certain industries even if it is unsupported for all firms together. Our intent, however, is to test the validity of the hypothesis as a general theory of intraurban location behavior. The paper consists of three sections. The first two present evidence on the "simple" and "dynamic" hypotheses. The final section summarizes our findings and offers some conclusions.
Handle: RePEc:nbr:nberwo:0045
Template-Type: ReDIF-Paper 1.0
Title: The Singular Value Analysis in Matrix Computation
Author-Name: Richard A. Becker
Author-Name: Neil Kaden
Author-Name: Virginia Klema
Number: 0046
Creation-Date: 1974-07
Order-URL: http://www.nber.org/papers/w0046
File-URL: http://www.nber.org/papers/w0046.pdf
File-Format: application/pdf
Abstract: This paper discusses the robustness and the computational stability of the singular value decomposition algorithm used at the NBER Computer Research Center. The effect of perturbations on input data is explored. Suggestions are made for using the algorithm to get information about the rank of a real square or rectangular matrix. The algorithm can also be used to compute the best approximate solution of linear system of equations in the least squares sense, to solve linear systems of equations with equality constraints, and to determine dependencies or near dependencies among the rows or columns of a matrix. A copy of the subroutine that is used and some examples on which it has been tested are included in the appendixes.
Handle: RePEc:nbr:nberwo:0046
Template-Type: ReDIF-Paper 1.0
Title: The Distribution of Earnings and Human Wealth in Cycle Context
Author-Name: Lee A. Lillard
Number: 0047
Creation-Date: 1974-07
Order-URL: http://www.nber.org/papers/w0047
File-URL: http://www.nber.org/papers/w0047.pdf
File-Format: application/pdf
Publication-Status: published as Lee A. Lillard, 1977. "The Distribution of Earnings and Human Wealth in a Life-Cycle Context," NBER Chapters, in: Distribution of Economic Well-Being, pages 557-620 National Bureau of Economic Research, Inc.
Publication-Status: published as Lillard, Lee A. "Inequality: Earnings Vs. Human Wealth," American Economic Review, 1977, v67(2), 42-53.
Abstract: The purpose of this paper is to outline a set of conditions under which human wealth is an index of well-being in a life cycle as prefatory to empirical estimates earnings and human wealth distributions for the1960 Census population.
Handle: RePEc:nbr:nberwo:0047
Template-Type: ReDIF-Paper 1.0
Title: Protection and Competitiveness in Egyptian Agriculture and Industry
Author-Name: Bent Hansen
Author-Name: Karim Nashashibi
Number: 0048
Creation-Date: 1974-07
Order-URL: http://www.nber.org/papers/w0048
File-URL: http://www.nber.org/papers/w0048.pdf
File-Format: application/pdf
Abstract: This paper contains the basic statistical material upon which Effective Rates of Protection (ERPs), Domestic Resource Costs (DRCs), and crop acreage responses were calculated by the authors for their volume on Egypt in the NBER project Foreign Trade Regimes and Economic Development. This material, which includes some comparisons of Egyptian costs of production with those of other countries for a number of commodities, is too extensive for that volume, in which interest is focused on the end results of the calculations. The underlying data, however, are not easily accessible: some of them took us along time to gather, and readers might want to work on the data themselves for further research in this field. We also felt that readers should be in a position to evaluate our calculations.
Handle: RePEc:nbr:nberwo:0048
Template-Type: ReDIF-Paper 1.0
Title: Years and Intensity of Schooling Investing
Author-Name: Arleen Leibowitz
Number: 0049
Creation-Date: 1974-08
Order-URL: http://www.nber.org/papers/w0049
File-URL: http://www.nber.org/papers/w0049.pdf
File-Format: application/pdf
Publication-Status: published as American Economic Review, Vol. 66, no. 3 (1976): 321-334.
Abstract: An essential feature of schooling is not only that it occurs in a different site than most on-the-job training but also that it is more intensive. That is, a smaller proportion of gross potential earnings is sacrificed in on-the-job training than in schooling. In estimating human capital earnings functions it has generally been assumed that during schooling 100% of gross potential earnings are invested in all years, while in on-the-job training this percentage is smaller and is a declining function of age. This assumption has been quite useful since it allows the identification of an estimate of the rate of return on schooling from a regression of earnings on years of schooling. This paper argues that the percentage of gross earnings invested may fall below 100% well before schooling is ended, that this percentage is likely to be correlated with years of schooling, and thus this procedure yields only a biased estimate of the rate of return to schooling.
Handle: RePEc:nbr:nberwo:0049
Template-Type: ReDIF-Paper 1.0
Title: Measuring the Effect of an Anti-Discrimination Program
Author-Name: Orley Ashenfelter
Author-Person: pas9
Author-Name: James J. Heckman
Number: 0050
Creation-Date: 1974-08
Order-URL: http://www.nber.org/papers/w0050
File-URL: http://www.nber.org/papers/w0050.pdf
File-Format: application/pdf
Publication-Status: published as Ashenfelter, Orley and James Heckman. "Measuring the Effect of an Anti-Discrimination Program." Evaluating the Labor-Market Effects of Social Programsedited by Orley Ashenfelter and James Blum, Princeton, NJ: Princeton University Press, 1976, pp. 46-89.
Abstract: Since 1941, six Executive Orders have been issued forbidding Federal government contractors from discriminating against minority workers. In principle, all prospective contractors are required to demonstrate compliance with the law before a contract is let. The potential penalties are severe: failure to comply with the law may result in revocation of current contracts and suspension of the right to bid on future contracts. Despite these provisions, doubts have been raised about the effectiveness of the Orders. Defenders of the Orders cite cases in which contract award dates have been postponed until firms have taken steps toward compliance with the law. In this paper, we investigate these competing claims using data from 40,445 establishments sampled in 1966 and 1970. In the first section of this paper, we distinguish what can be measured from what cannot. We develop a framework to measure and interpret program effects. In the second section we discuss the design of our sample and present results of an analysis of the randomness of this sample. In the third and concluding section, we present the estimates and discuss their plausibility.
Handle: RePEc:nbr:nberwo:0050
Template-Type: ReDIF-Paper 1.0
Title: Age, Experience and Wage Growth
Author-Name: Edward P. Lazear
Author-Person: pla64
Number: 0051
Creation-Date: 1974-08
Order-URL: http://www.nber.org/papers/w0051
File-URL: http://www.nber.org/papers/w0051.pdf
File-Format: application/pdf
Publication-Status: published as Lazear, Edward. "Age, Experience and Wage Growth." American Economic Review , (September 1976). The American Economic Review. Vol.66, number4, pp.548-558, September 1976
Abstract: During the past decade, much has been said about the role that on-the-job training plays in augmenting one's stock of human capital. Up to this point, little has been done to distinguish the effect of on-the-job training from that of aging on the increase in human wealth. The reason rests primarily on the fact that it is difficult to observe or even define in some appropriate way the amount of on-the-job training that an individual possesses. In this paper, a method is developed by which one may compare the effects of work experience to those of aging per se. The difference is then attributed to on-the-job training.
Handle: RePEc:nbr:nberwo:0051
Template-Type: ReDIF-Paper 1.0
Title: Transportation/Communication Considerations in the Location of Headquarters for Multi-Establishment Manufacturing Firms
Author-Name: Warren G. Lavey
Number: 0052
Creation-Date: 1974-08
Order-URL: http://www.nber.org/papers/w0052
File-URL: http://www.nber.org/papers/w0052.pdf
File-Format: application/pdf
Abstract: Usually transportation/communication (t/c) considerations appear as only two in a long list of factors which determine headquarters location patterns. The research reported here singles out t/c considerations as the logical basis for headquarters location decisions. We ask: to what degree do transportation/communication consideration explain the patterns of headquarters location? The case of manufacturing firms with five or more establishments and no manufacturing activity at the headquarters location was examined. The t/c considerations were studied in terms of the advantages of close proximity between the headquarters of a firm and the manufacturing establishments of that firm and the advantages of close proximity between the headquarters of one firm and the headquarters of other firms. The findings of this research show that the logic of headquarters location patterns is heavily dependent on t/c considerations.
Handle: RePEc:nbr:nberwo:0052
Template-Type: ReDIF-Paper 1.0
Title: Progress in Human Capital Analysis of the Distribution of Earnings
Author-Name: Jacob Mincer
Number: 0053
Creation-Date: 1974-08
Order-URL: http://www.nber.org/papers/w0053
File-URL: http://www.nber.org/papers/w0053.pdf
File-Format: application/pdf
Publication-Status: published as Mincer, Jacob. "Progress in Human Capital Analysis of the Distribution of Earnings." The Personal Distribution of Incomes, edited by A.B. Atkinson. London, England: Allen & Unwin, 1976.
Abstract: The traditional studies of income distribution, a field with which economists are becoming increasingly concerned, must be described as basically sociological. The ascendancy of the human capital approach can be viewed as a reaction of economists to this non-economic, though certainly not irrelevant, tradition. In stressing the role played by individual and family optimizing decisions in human capital investments, important aspects of income determination are brought back within the mainstream of economic theory and within the power of its analytical and econometric tools. Human capital is not the only element of choice in the analysis of income distribution . Nevertheless, it appears that the subject of human capital investments lends itself to a more systematic and comprehensive analysis of wage differentials, than each of the other factors. The following is a description of research in the distribution of labor incomes in which human capital theory serves as an organizing principle. It is, in part, a sequel to my 1970 survey and, in part, a report of ongoing research of my own and of others.
Handle: RePEc:nbr:nberwo:0053
Template-Type: ReDIF-Paper 1.0
Title: Bilateral Trade as a Development Instrument Under Global Trade Restrictions
Author-Name: Karim Nashashibi
Number: 0054
Creation-Date: 1974-08
Order-URL: http://www.nber.org/papers/w0054
File-URL: http://www.nber.org/papers/w0054.pdf
File-Format: application/pdf
Abstract: In their striving toward development, a number of less developed countries have espoused bilateral trade as yet another policy instrument allowing them to increase their acquisition of foreign resources. This has been particularly true of the trade of India, Pakistan, and Egypt, on which some useful empirical studies have been conducted. The target we are interested in is not trade efficiency as an end in itself, but growth. For a number of countries, the ability to grow depends very much on the ability to import. Hence, it is in terms of this target that we propose to evaluate the efficiency of bilateral trade as a policy instrument and to examine a number of related issues, such as the terms of trade, trade diversion, and its effect on resource allocation. A brief description of bilateral trade agreements starts our discussion followed by a three-country model as a theoretical formulation of the problem. Finally, several implications will be derived in relation to the issues mentioned above.
Handle: RePEc:nbr:nberwo:0054
Template-Type: ReDIF-Paper 1.0
Title: Social Costs of Monopoly and Regulation
Author-Name: Richard A. Posner
Author-Person: ppo25
Number: 0055
Creation-Date: 1974-09
Order-URL: http://www.nber.org/papers/w0055
File-URL: http://www.nber.org/papers/w0055.pdf
File-Format: application/pdf
Publication-Status: published as Richard A. Posner, 1975. "The Social Costs of Monopoly and Regulation," Journal of Political Economy, vol 83(4), pages 807-827.
Abstract: When an industry is monopolized, price rises above and output falls below the competitive level. Those who continue to buy the product at the higher price suffer a loss, but this loss is exactly offset by the additional revenue that the monopolist obtains by charging the higher price. Other consumers, who are deflected by the higher price to substitute goods, suffer a loss, that is not offset by gains to the monopolist. This is the "deadweight loss" from monopoly, and in conventional analysis the only social cost of monopoly. The loss suffered by those who continue to buy the product at the higher cost is regarded merely as a transfer from consumers to owners of the monopoly seller and has not previously been factored into the social costs of monopoly. However, the existence of an opportunity to obtain monopoly profits will attract resources into efforts to obtain monopolies, and the opportunity costs of those resources are social costs of monopoly, too. Although the tendency of monopoly rents to be transformed into costs is no longer a novel insight, its implications both for the measurement of the aggregate social costs of monopoly and for a variety of other important issues relating to monopoly and public regulation (including tax policy) continue to be ignored. The present paper is an effort to rectify this neglect. Part I introduces the material. Part II presents a simple model of the social costs of monopoly, conceived as the sum of the deadweight loss and the additional loss resulting from the competition to become a monopolist. Part III uses the model to estimate the social costs of monopoly in the United States, and the social benefits of antitrust enforcement. Part IV explores the implications of the analysis for a variety of issues relating to monopoly and public regulation, such as public policy toward price discrimination and the choice between income and excise taxation.
Handle: RePEc:nbr:nberwo:0055
Template-Type: ReDIF-Paper 1.0
Title: Comparison of Robust and Varying Parameter Estimates of a Macroeconometric Model
Author-Name: Thomas F. Cooley
Author-Person: pco35
Number: 0056
Creation-Date: 1974-09
Order-URL: http://www.nber.org/papers/w0056
File-URL: http://www.nber.org/papers/w0056.pdf
File-Format: application/pdf
Publication-Status: published as Cooley, Thomas F. "Comparison of Robust and Varying Parameter Estimates of a Macroeconometric Model." Annals of Economic and Social Measurement, Vol. 4, No. 3, (1975), pp. 373-388.
Abstract: Four estimators of econometric models are compared for predictive accuracy. Two estimators assume that the parameters of the equations are subject to variation over time. The first of these, the adaptive regression technique (ADR), assumes that the intercept varies overtime, while the other, a varying-parameter regression technique (VPR), assumes that all parameters may be subject to variation. The other two estimators are ordinary least squares (OLS) and a robust estimator that gives less weight to large residuals. The vehicle for these experiments is the econometric model developed by Ray Fair. The main conclusion is that varying parameter techniques appear promising for the estimation of econometric models. They are clearly superior in the present context for short term forecasts. Of the two varying parameter techniques considered, ADR is superior over longer prediction intervals.
Handle: RePEc:nbr:nberwo:0056
Template-Type: ReDIF-Paper 1.0
Title: Varying-Parameter Supply Functions and the Sources of Economic Distress in American Agriculture, 1866-1914
Author-Name: Thomas F. Cooley
Author-Person: pco35
Author-Name: Steven J. DeCanio
Number: 0057
Creation-Date: 1974-09
Order-URL: http://www.nber.org/papers/w0057
File-URL: http://www.nber.org/papers/w0057.pdf
File-Format: application/pdf
Publication-Status: published as Cooley, Thomas F. and DeCanio, Steven J. "Varying-Parameter Supply Functions and the Sources of Economic Distresss in American Agriculture, 1866-1914." The Review of Economics and Statistics, Vol. LIX, No. 1, (February 1977).
Abstract: The agrarian unrest in the United States at the end of the nineteenth century is examined. This unrest is often viewed as stemming from the inability of farmers to adapt to changing conditions in world agriculture. This hypothesis is tested in the context of a distributed lag supply function. Varying parameter estimation methods are used to trace the history of the parameters in the supply function and to decompose observed prices into permanent and transitory components over time. The patterns of variation are tested for conformity with a model of rational price-expectation formation. The conclusion is that farmers behaved as economic theory would predict, but that neither theory nor practice gave them relief from the troubles which plagued them.
Handle: RePEc:nbr:nberwo:0057
Template-Type: ReDIF-Paper 1.0
Title: A Monte Carlo Study of Two Robust Alternatives of Least Square Regression Estimation
Author-Name: Richard W. Hill
Author-Name: Paul W. Holland
Number: 0058
Creation-Date: 1974-09
Order-URL: http://www.nber.org/papers/w0058
File-URL: http://www.nber.org/papers/w0058.pdf
File-Format: application/pdf
Publication-Status: published as Hill, Richard W. and Paul W. Holland. "Two Robust Alternatives To Least-Squared Regression," Journal of the American Statistical Association, 1977, v72(360), 828-833.
Abstract: We give some Monte Carlo results on the performance of two robust alternatives to least squares regression estimation - least absolute residuals and the one-step "sine" estimator. We show how to scale the residuals for the sine estimator to achieve constant efficiency at the Gaussian across various choices of X-matrix and give some results for the contaminated Gaussian distribution.
Handle: RePEc:nbr:nberwo:0058
Template-Type: ReDIF-Paper 1.0
Title: An Analysis of Firm Demand for Protection Against Crime
Author-Name: Ann P. Bartel
Number: 0059
Creation-Date: 1974-10
Order-URL: http://www.nber.org/papers/w0059
File-URL: http://www.nber.org/papers/w0059.pdf
File-Format: application/pdf
Publication-Status: published as Bartel, Ann P. "An Analysis of Firm Demand for Protection Against Crime." Journal of Legal Studies, Vol. IV, No. 2, (June 1975), pp. 443-478.
Abstract: It is well known that as a result of spiralling crime rates, public expenditures for police protection have been rising at a rapid rate. It is less well known, however, that private expenditures for guards, protective services and equipment have kept pace with the increasing public expenditures. Despite the fact that in 1970 the private sector allocated at least $3.3 billion of its resources to protection, and this sum is two-thirds the size of the corresponding public outlay, no one has explicitly analyzed the determinants of the private sector's demand for protection. This article, which summarizes a larger study, attempts to fill this gap by considering firm demand for protection. The main purpose of this article is to answer three questions. One, how is firm demand for protection related to business losses from crime and the probability of crime? Two, are public and private expenditures substitutes or complements? Three, does a firm choose self-protection as a substitute for market insurance or will it spend more on protection if it has insurance? Part I describes a theoretical framework for analyzing a firm's protection decisions. In Part II I discuss the data set that is used to test the model and the methods of proxying some of the unobserved theoretical variables. Part III presents the results of the empirical analysis. In Part IV the data are used to test what factors, holding protection expenditures constant, predict whether or not a firm will be victimized.
Handle: RePEc:nbr:nberwo:0059
Template-Type: ReDIF-Paper 1.0
Title: The Variances of Regression Coefficient Estimates Using Aggregate Data
Author-Name: Roy E. Welsch
Author-Name: Edwin Kuh
Number: 0060
Creation-Date: 1974-10
Order-URL: http://www.nber.org/papers/w0060
File-URL: http://www.nber.org/papers/w0060.pdf
File-Format: application/pdf
Publication-Status: published as Econometrica, Vol. 44, no. 2 (1976): 353-364.
Abstract: This paper considers the effect of aggregation on the variance of parameter estimates for a linear regression model with random coefficients and an additive error term. Aggregate and microvariances are compared and measures of relative efficiency are introduced. Necessary conditions for efficient aggregation procedures are obtained from the Theil aggregation weights and from measures of synchronization related to the work of Grunfeld and Griliches.
Handle: RePEc:nbr:nberwo:0060
Template-Type: ReDIF-Paper 1.0
Title: Factoring LP Block-Angular Bases
Author-Name: William Orchard-Hays
Number: 0061
Creation-Date: 1974-11
Order-URL: http://www.nber.org/papers/w0061
File-URL: http://www.nber.org/papers/w0061.pdf
File-Format: application/pdf
Publication-Status: published as Computational Practice in Mathematical Programming, Mathematical Programming Studies Volume 4. Springer Berlin Heidelberg, 1975.
Abstract: A factorization of the basis for any block-angular 12 model is presented, and its inverse is shown to be readily maintainable as piecemeal product-forms plus possible additional columns. Straightforward rules for piecemeal transformation of full rows and columns are given.
Handle: RePEc:nbr:nberwo:0061
Template-Type: ReDIF-Paper 1.0
Title: The Private Enforcement of Law
Author-Name: William M. Landes
Author-Person: pla327
Author-Name: Richard A. Posner
Author-Person: ppo25
Number: 0062
Creation-Date: 1974-11
Order-URL: http://www.nber.org/papers/w0062
File-URL: http://www.nber.org/papers/w0062.pdf
File-Format: application/pdf
Publication-Status: published as Landes, William M. and Posner, Richard A. "The Private Enforcement of Law." Journal of Legal Studies, (January 1975).
Abstract: An important question in the economic study of enforcement is the appropriate, and the actual, division of responsibilities between public and private enforcers. This question has been brought into sharp focus recently by an article in which Gary Becker and George Stigler advocate the privatization of law enforcement. In the present article, we explore the idea that the area in which private enforcement is in fact clearly preferable to public enforcement on efficiency grounds is more restricted than Becker and Stigler believe; perhaps the existing division of enforcement between the public and private sectors approximates the optimal division. Part I develops an economic model of competitive, profit-maximizing private enforcement. The model predicts the level of enforcement and the number of offenses that would occur in a world of exclusively private enforcement. Part II refines the model to account for the presence of monopoly in the private enforcement industry, different assignments of property rights in legal claims, the effect of taxing private enforcers, nonmonetary penalties, and legal errors - elements ignored in the initial development of the model in Part I. Part III contrasts our model with other economic approaches to the enforcement question. Part IV presents a number of positive implications of the model, relating to the choice between public and private enforcement of criminal versus civil laws, the assignment of exclusive rights to the victims of offenses, the budgets of public agencies, the discretionary nonenforcement of the law, and the legal treatment of blackmail and bribery. The positive implications of the model appear to be consistent with observations of the real world, although the findings in Part IV must be regarded as highly tentative. An appendix discusses the economics of rewards - an important method of compensating private enforcers.
Handle: RePEc:nbr:nberwo:0062
Template-Type: ReDIF-Paper 1.0
Title: Censored Regression Models with Unobserved Stochastic Censoring Thresholds
Author-Name: Forrest D. Nelson
Number: 0063
Creation-Date: 1974-12
Order-URL: http://www.nber.org/papers/w0063
File-URL: http://www.nber.org/papers/w0063.pdf
File-Format: application/pdf
Publication-Status: published as Journal of Econometrics, Vol. 6, no. 3 (1977): 309-328.
Abstract: The "Tobit" model is a useful tool for estimation of regression models with a truncated or limited dependent variable, but it requires a threshold which is either a known constant or an observable and independent variable. The model presented here extends the Tobit model to the censored case where the threshold is an unobserved and not necessarily independent random variable. Maximum likelihood procedures can be employed for joint estimation of both the primary regression equation and the parameters of the distribution of that random threshold. The appropriate likelihood function is derived, the conditions necessary for identification are revealed, and the particular estimation difficulties are discussed. The model is illustrated by an application to the determination of a housewife's value of time.
Handle: RePEc:nbr:nberwo:0063
Template-Type: ReDIF-Paper 1.0
Title: Data Analysis, Communication, and Control
Author-Name: Roy E. Welsch
Number: 0064
Creation-Date: 1974-12
Order-URL: http://www.nber.org/papers/w0064
File-URL: http://www.nber.org/papers/w0064.pdf
File-Format: application/pdf
Publication-Status: published as Krippendorff (ed.) Communication and Control in Society. Routledge, 1979.
Abstract: The role of data analysis in communication, persuasion, and decision-making is discussed. Some problems with current data-analysis practice are presented, including communication, complex models, large data bases, one-pass processing, rigid assumptions, resistance, validity, prior information, access to new methods, and the responsiveness of data analysis researchers to real world needs. Recent progress in these areas is then outlined, with emphasis on graphics, Bayesian regression, robust estimation, and jackknife, and interactive computing systems. Some remaining challenges for data analysts and others who are trying to integrate data into decision-making processes are discussed.
Handle: RePEc:nbr:nberwo:0064
Template-Type: ReDIF-Paper 1.0
Title: Rational Distributed Lag Structural Form--A General Econometric Model
Author-Name: Kent D. Wall
Number: 0065
Creation-Date: 1974-12
Order-URL: http://www.nber.org/papers/w0065
File-URL: http://www.nber.org/papers/w0065.pdf
File-Format: application/pdf
Abstract: The Rational Distributed Lag Structural Form of an econometric model is introduced, and its relationship to several traditional forms of representation is discussed. The traditional forms are viewed as special cases of the Rational Structural Form. Thus, the latter provides a unified framework for any treatment of the linear, time invariant modeling problem. In particular, a solution of the estimation problem for the Rational Structural Form leads to the solution of the estimation problem for all traditional forms.
Handle: RePEc:nbr:nberwo:0065
Template-Type: ReDIF-Paper 1.0
Title: Detecting and Assessing the Problems Caused by Multi-Collinearity: A Useof the Singular-Value Decomposition
Author-Name: David A. Belsley
Author-Name: Virginia Klema
Number: 0066
Creation-Date: 1974-12
Order-URL: http://www.nber.org/papers/w0066
File-URL: http://www.nber.org/papers/w0066.pdf
File-Format: application/pdf
Abstract: This paper presents a means for detecting the presence of multicollinearity and for assessing the damage that such collinearity may cause estimated coefficients in the standard linear regression model. The means of analysis is the singular value decomposition, a numerical analytic device that directly exposes both the conditioning of the data matrix X and the linear dependencies that may exist among its columns. The same information is employed in the second part of the paper to determine the extent to which each regression coefficient is being adversely affected by each linear relation among the columns of X that lead to its ill conditioning.
Handle: RePEc:nbr:nberwo:0066
Template-Type: ReDIF-Paper 1.0
Title: On a General Computer Algorithm for the Analysis of Models with Limited Dependent Variables
Author-Name: Forrest D. Nelson
Number: 0068
Creation-Date: 1974-10
Order-URL: http://www.nber.org/papers/w0068
File-URL: http://www.nber.org/papers/w0068.pdf
File-Format: application/pdf
Publication-Status: published as (Published as "Specification and Estimation of a Simultaneous-Equation Model with Limited Dependent Variables") International Economic Review, Vol. 19, no. 3 (1978): 695-710.
Publication-Status: published as On a General Computer Algorithm for the Analysis of Models with Limited Dependent Variables, Forrest D. Nelson. in Annals of Economic and Social Measurement, Volume 5, number 4, Berg. 1976
Abstract: Several econometric models for the analysis of relationships with limited dependent variables have been proposed, including the probit, Tobit, two-limit probit, ordered discrete, and friction models. Widespread application of these methods has been hampered by the lack of suitable computer programs. This paper provides a concise survey of the various models; suggests a general functional model under which they may be formulated and analyzed; reviews the analytic problems and the similarities and dissimilarities of the models; and outlines the appropriate and necessary methods of analysis including, but not limited to, estimation. It is thus intended to serve as a guide for users of the various models, for the preparation of suitable computer programs, for the users of those programs; and, more specifically, for the users of the program package utilizing the functional model as implemented on the NBER TROLL system.
Handle: RePEc:nbr:nberwo:0068
Template-Type: ReDIF-Paper 1.0
Title: Ridge Estimators for Distributed Lag Models
Author-Name: G.S. Maddala
Number: 0069
Creation-Date: 1974-10
Order-URL: http://www.nber.org/papers/w0069
File-URL: http://www.nber.org/papers/w0069.pdf
File-Format: application/pdf
Publication-Status: published as Maddala, G. S. (ed.) Econometric methods and applications. Volume 1., Economists of the Twentieth Century series. Aldershot, U.K.: Elgar, 1994.
Abstract: The paper explains how the Almon polynominal lag specification can be made stochastic in two different ways - one suggested by Shiller and another following the lines of Lindley and Smith. It is shown that both the estimators can be considered as modified ridge estimators. The paper then compares these modified ridge estimators with the ridge estimator suggested by Hoerl and Kennard. It is shown that for the estimation of distributed lag models the ridge estimator suggested by Hoerl and Kennard is not useful but that the modified ridge estimators corresponding to the stochastic versions of the Almon lag are promising. The paper has two empirical illustrations.
Handle: RePEc:nbr:nberwo:0069
Template-Type: ReDIF-Paper 1.0
Title: Analysis of Qualitative Variables
Author-Name: G.S. Maddala
Author-Name: Forrest D. Nelson
Number: 0070
Creation-Date: 1974-10
Order-URL: http://www.nber.org/papers/w0070
File-URL: http://www.nber.org/papers/w0070.pdf
File-Format: application/pdf
Abstract: A variety of qualitative dependent variable models are surveyed with attention focused on the computational aspects of their analysis. The models covered include single equation dichotomous models; single equation polychotomous models with unordered, ordered, and sequential variables; and simultaneous equation models. Care is taken to illucidate the nature of the suggested "full information" and "limited information" approaches to the simultaneous equation models and the formulation of recursive and causal chain models.
Handle: RePEc:nbr:nberwo:0070
Template-Type: ReDIF-Paper 1.0
Title: The Goodness of Match
Author-Name: Edward N. Wolff
Number: 0072
Creation-Date: 1974-12
Order-URL: http://www.nber.org/papers/w0072
File-URL: http://www.nber.org/papers/w0072.pdf
File-Format: application/pdf
Abstract: Though the statistical techniques vary, the matching problem is essentially the same in each case and can be stated formally as follows: Given "observations on X,Y from one sample and on X,Z from another sample, when will it be true that by matching observations according to X, an artificial Y,Z sample will result whose distribution is the true joint Y,Z distribution?"(Sims,1972, p. 355). Though the imputed Y,Z distribution will, in general, be different from the true Y,Z distribution, the closeness of the two yields a natural criterion of the goodness of match. By making certain simplifying assumptions, we can make this criterion operational. The goodness of match depends on how much of the relation between Y and Z is transmitted through X - that is, on how X "mediates" between Y and Z. Since the functional form the lower and upper bounds on the true correlation between Y and Z takes depends on the number of X variables, we shall treat the problem in three stages: (a) The case of one mediating variable.(b) The case of two mediating variables. (c) The case of n mediating variables.
Handle: RePEc:nbr:nberwo:0072